Deep learning (DL) models have been advancing automatic
medical image analysis on various modalities, including echocardiogra-
phy, by offering a comprehensive end-to-end training pipeline. This ap-
proach enables DL models to regress ejection fraction (EF) directly from
2D+time echocardiograms, resulting in superior performance. However,
the end-to-end training pipeline makes the learned representations less
explainable. The representations may also fail to capture the contin-
uous relation among echocardiogram clips, indicating the existence of
spurious correlations, which can negatively affect the generalization. To
mitigate this issue, we propose CoReEcho, a novel training framework
emphasizing continuous representations tailored for direct EF regres-
sion. Our extensive experiments demonstrate that CoReEcho: 1) outper-
forms the current state-of-the-art (SOTA) on the largest echocardiog-
raphy dataset (EchoNet-Dynamic) with MAE of 3.90 & R2 of 82.44,
and 2) provides robust and generalizable features that transfer more ef-
fectively in related downstream tasks.
Paper Link: https://arxiv.org/pdf/2403.10164